© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 8-RES-JB
    11. 22436
    Prev
    Next
    INDEX
    Explanations

    specific acronyms or initialisms

    oai_token-act-pair · gpt-3.5-turbo

    identifiers or acronyms related to entities or organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    taboola
    -0.83
    ItemTracker
    -0.71
    licted
    -0.66
    alam
    -0.62
    jar
    -0.61
    give
    -0.60
    ighton
    -0.60
     spe
    -0.59
    scl
    -0.57
     glowing
    -0.57
    POSITIVE LOGITS
    ELS
    1.12
    ATA
    1.11
    AR
    1.10
    OT
    1.10
    OPS
    1.08
    ETS
    1.07
    OSS
    1.07
    ARE
    1.06
    ITION
    1.05
    KA
    1.05
    Activations Density 0.158%

    No Known Activations